Different inference resullt

[Jiaxin Wen]

Hi,
I've tested a number of cases either using code&&parameter from this repo or demo from https://mosaickg.apps.allenai.org/comet_atomic. And I'm kind of confused as there have obvious differences in the results. So what's the exact difference between them?
Thanks

[Antoine Bosselut]

Are you using a pretrained model or retraining a model using the code?

Which decoder are you using to decode sequences?